Past talk · AI/ML Seminar Series
Provably Personalized and Robust Federated Learning
PhD Student, Department of Electrical Engineering and Computer Science, UC Berkeley
- Date & time
- Monday, November 6, 2023 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
I will be discussing my recent work on personalization in federated learning. Federated learning is a powerful distributed optimization framework in which multiple clients collaboratively train a global model without sharing their raw data. In this work, we tackle the personalized version of the federated learning problem. In particular, we ask: throughout the training process, can clients identify a subset of similar clients and collaboratively train with just those clients? In the affirmative, we propose simple clustering-based methods which are provably optimal for a broad class of loss functions, are robust to malicious attackers, and perform well in practice.
About the speaker
Mariel Werner is a 5th-year PhD student in the Department of Electrical Engineering and Computer Science at UC Berkeley advised by Michael I. Jordan. Her research focus is federated learning, with a particular interest in economic applications. Mariel holds an undergraduate degree in Applied Mathematics from Harvard University.